Skip to content

Agent Tooling

Skills that build, configure or extend agents and other skills.

Search and filter within Agent Tooling

12964 skills

app-builderSouvik-223/agent-skills-agentic-toolsMain application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.Stars: 0Updated Claude CodeCodexVerifiedInstall
app-builderSouvik-223/agent-skills-agentic-toolsMain application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.Stars: 0Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-conflicting-evidence-build-configuration-runbookManoj-11-Dahal/try-SkillsUse when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for conflicting evidence. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Report regressions and evaluator conflicts separately; do not hide a loss in one held-out case behind an aggregate score. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-conflicting-evidence-failure-triage-and-recoveryManoj-11-Dahal/try-SkillsUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for conflicting evidence. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Report regressions and evaluator conflicts separately; do not hide a loss in one held-out case behind an aggregate score. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-conflicting-evidence-requirements-and-decision-briefManoj-11-Dahal/try-SkillsUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for conflicting evidence. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Report regressions and evaluator conflicts separately; do not hide a loss in one held-out case behind an aggregate score. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-conflicting-evidence-scope-and-baseline-recordManoj-11-Dahal/try-SkillsUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for conflicting evidence. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Report regressions and evaluator conflicts separately; do not hide a loss in one held-out case behind an aggregate score. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-conflicting-evidence-source-research-and-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision depends on current, source-grounded information for Human-governed agent improvement: evaluator integrity for conflicting evidence. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Report regressions and evaluator conflicts separately; do not hide a loss in one held-out case behind an aggregate score. Success means material claims are linked to current primary sources with dates and limitations. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-long-horizon-tasks-build-configuration-runbookManoj-11-Dahal/try-SkillsUse when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for long-horizon tasks. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Persist a baseline checkpoint and a bounded change proposal; do not convert project duration into permission to alter the agent. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-long-horizon-tasks-failure-triage-and-recoveryManoj-11-Dahal/try-SkillsUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for long-horizon tasks. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Persist a baseline checkpoint and a bounded change proposal; do not convert project duration into permission to alter the agent. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-long-horizon-tasks-requirements-and-decision-briefManoj-11-Dahal/try-SkillsUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for long-horizon tasks. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Persist a baseline checkpoint and a bounded change proposal; do not convert project duration into permission to alter the agent. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-long-horizon-tasks-scope-and-baseline-recordManoj-11-Dahal/try-SkillsUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for long-horizon tasks. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Persist a baseline checkpoint and a bounded change proposal; do not convert project duration into permission to alter the agent. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-long-horizon-tasks-source-research-and-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision depends on current, source-grounded information for Human-governed agent improvement: evaluator integrity for long-horizon tasks. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Persist a baseline checkpoint and a bounded change proposal; do not convert project duration into permission to alter the agent. Success means material claims are linked to current primary sources with dates and limitations. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-missing-acceptance-criteria-build-configuration-runbookManoj-11-Dahal/try-SkillsUse when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for missing acceptance criteria. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Add an explicit testable acceptance criterion and evaluator version before proposing a skill update. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-missing-acceptance-criteria-failure-triage-and-recoveryManoj-11-Dahal/try-SkillsUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for missing acceptance criteria. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Add an explicit testable acceptance criterion and evaluator version before proposing a skill update. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-missing-acceptance-criteria-requirements-and-decision-briefManoj-11-Dahal/try-SkillsUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for missing acceptance criteria. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Add an explicit testable acceptance criterion and evaluator version before proposing a skill update. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-missing-acceptance-criteria-scope-and-baseline-recordManoj-11-Dahal/try-SkillsUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for missing acceptance criteria. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Add an explicit testable acceptance criterion and evaluator version before proposing a skill update. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-missing-acceptance-criteria-source-research-and-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision depends on current, source-grounded information for Human-governed agent improvement: evaluator integrity for missing acceptance criteria. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Add an explicit testable acceptance criterion and evaluator version before proposing a skill update. Success means material claims are linked to current primary sources with dates and limitations. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-multi-session-projects-build-configuration-runbookManoj-11-Dahal/try-SkillsUse when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for multi-session projects. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Store proposed lessons with source, time, confidence, and review status; never merge unreviewed session notes into active instructions. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-multi-session-projects-failure-triage-and-recoveryManoj-11-Dahal/try-SkillsUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for multi-session projects. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Store proposed lessons with source, time, confidence, and review status; never merge unreviewed session notes into active instructions. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-multi-session-projects-requirements-and-decision-briefManoj-11-Dahal/try-SkillsUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for multi-session projects. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Store proposed lessons with source, time, confidence, and review status; never merge unreviewed session notes into active instructions. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-multi-session-projects-scope-and-baseline-recordManoj-11-Dahal/try-SkillsUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for multi-session projects. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Store proposed lessons with source, time, confidence, and review status; never merge unreviewed session notes into active instructions. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-multi-session-projects-source-research-and-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision depends on current, source-grounded information for Human-governed agent improvement: evaluator integrity for multi-session projects. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Store proposed lessons with source, time, confidence, and review status; never merge unreviewed session notes into active instructions. Success means material claims are linked to current primary sources with dates and limitations. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-partial-completion-build-configuration-runbookManoj-11-Dahal/try-SkillsUse when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for partial completion. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-partial-completion-failure-triage-and-recoveryManoj-11-Dahal/try-SkillsUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for partial completion. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-partial-completion-requirements-and-decision-briefManoj-11-Dahal/try-SkillsUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for partial completion. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-partial-completion-scope-and-baseline-recordManoj-11-Dahal/try-SkillsUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for partial completion. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-partial-completion-source-research-and-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision depends on current, source-grounded information for Human-governed agent improvement: evaluator integrity for partial completion. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means material claims are linked to current primary sources with dates and limitations. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-strict-tool-call-budgets-build-configuration-runbookManoj-11-Dahal/try-SkillsUse when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-strict-tool-call-budgets-failure-triage-and-recoveryManoj-11-Dahal/try-SkillsUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall
selfupdate-evaluator-integrity-strict-tool-call-budgets-requirements-and-decision-briefManoj-11-Dahal/try-SkillsUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.Stars: 3Updated Claude CodeCodexVerifiedInstall